INDEX

Explanations

words related to averages and typical values

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 DialogInterface

-0.71

sk

-0.69

̀n

-0.68

re

-0.67

sp

-0.66

Je

-0.65

 Kirk

-0.64

Gun

-0.63

Hel

-0.63

 Robertson

-0.63

POSITIVE LOGITS

 Average

1.87

 AVERAGE

1.84

Average

1.83

 average

1.83

average

1.81

 averages

1.77

AVERAGE

1.77

 averaging

1.67

verages

1.62

Avg

1.60

Activations Density 0.064%

words related to averages and typical values

No Comments

No Known Activations